© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177017
    Prev
    Next
    INDEX
    Explanations

    language and culture

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AEG
    0.43
     AE
    0.41
     æ
    0.40
     Gage
    0.40
     aes
    0.39
    稲
    0.39
     Le
    0.39
    gae
    0.39
     Effect
    0.38
    硃
    0.38
    POSITIVE LOGITS
    ivamente
    0.40
    lic
    0.40
    lick
    0.39
     پرومو
    0.38
     sing
    0.38
    িয়াল
    0.37
    ifer
    0.37
    ftar
    0.37
    Alan
    0.37
     fart
    0.37
    Activations Density 0.005%

    No Known Activations